Python 基于多类分类的CNN模型过拟合
我正在尝试使用手套嵌入来训练一个基于(也是一个rnn的)cnn模型。数据集是一个标签数据:文本(tweets)和标签(仇恨、冒犯或两者都没有) 问题在于,模型在训练集上表现良好,但在验证集上表现不佳 模型如下:Python 基于多类分类的CNN模型过拟合,python,keras,deep-learning,conv-neural-network,recurrent-neural-network,Python,Keras,Deep Learning,Conv Neural Network,Recurrent Neural Network,我正在尝试使用手套嵌入来训练一个基于(也是一个rnn的)cnn模型。数据集是一个标签数据:文本(tweets)和标签(仇恨、冒犯或两者都没有) 问题在于,模型在训练集上表现良好,但在验证集上表现不佳 模型如下: kernel_size = 2 filters = 256 pool_size = 2 gru_node = 64 model = Sequential() model.add(Embedding(len(word_index) + 1,
kernel_size = 2
filters = 256
pool_size = 2
gru_node = 64
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True))
model.add(Dropout(0.25))
model.add(Conv1D(filters, kernel_size, activation='relu'))
model.add(MaxPooling1D(pool_size=pool_size))
model.add(Conv1D(filters, kernel_size, activation='softmax'))
model.add(MaxPooling1D(pool_size=pool_size))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, recurrent_dropout=0.2))
model.add(Dense(1024,activation='relu'))
model.add(Dense(nclasses))
model.add(Activation('softmax'))
model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
X = df.tweet
y = df['classifi'] # classes 0,1,2
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, shuffle=False)
X_train_Glove,X_test_Glove, word_index,embeddings_index = loadData_Tokenizer(X_train,X_test)
model_RCNN = Build_Model_RCNN_Text(word_index,embeddings_index, 20)
model_RCNN.fit(X_train_Glove, y_train,validation_data=(X_test_Glove, y_test),
epochs=15,batch_size=128,verbose=2)
predicted = model_RCNN.predict(X_test_Glove)
predicted = np.argmax(predicted, axis=1)
print(metrics.classification_report(y_test, predicted))
拟合模型:
kernel_size = 2
filters = 256
pool_size = 2
gru_node = 64
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=True))
model.add(Dropout(0.25))
model.add(Conv1D(filters, kernel_size, activation='relu'))
model.add(MaxPooling1D(pool_size=pool_size))
model.add(Conv1D(filters, kernel_size, activation='softmax'))
model.add(MaxPooling1D(pool_size=pool_size))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, return_sequences=True, recurrent_dropout=0.2))
model.add(LSTM(gru_node, recurrent_dropout=0.2))
model.add(Dense(1024,activation='relu'))
model.add(Dense(nclasses))
model.add(Activation('softmax'))
model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
X = df.tweet
y = df['classifi'] # classes 0,1,2
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, shuffle=False)
X_train_Glove,X_test_Glove, word_index,embeddings_index = loadData_Tokenizer(X_train,X_test)
model_RCNN = Build_Model_RCNN_Text(word_index,embeddings_index, 20)
model_RCNN.fit(X_train_Glove, y_train,validation_data=(X_test_Glove, y_test),
epochs=15,batch_size=128,verbose=2)
predicted = model_RCNN.predict(X_test_Glove)
predicted = np.argmax(predicted, axis=1)
print(metrics.classification_report(y_test, predicted))
这就是分布的样子(0:仇恨,1:攻击,2:都不是)
模型摘要
结果:
这是正确的方法还是我在这里遗漏了什么一般来说,有两个方面可以解决过度装配的问题:
- 更独特的数据
- 过采样(平衡数据)
- 辍学(你已经实现了这一点)
- 更少的参数(您可能希望针对更小的网络进行基准测试)
- 正则化(例如L1和L2)
祝你好运 第一层有1M的参数。我不知道这是否是故意的,但它看起来很大